EEG based Intelligent robot chair with communication aid using statistical cross correlation based features

In this research work, a Thought Controlled Intelligent robot chair with communication aid has been developed. A simple brain wave data acquisition protocol has been developed with seven basic tasks that can be used for both robot chair control and communication system. The proposed system records the 19-channel electroencephalography signal while mentally executing the tasks. The recorded brain wave signals are pre-processed to remove the interference waveforms and segmented into four frequency bands. The frequency band signals are used to extract the features using Band Power features to optimize the electrode channels using a combination without repetition analysis. Hence, the raw brain wave signals of the selected electrode channels are pre-processed and used to extract the cross-correlation coefficients between any two frequency bands. Similarly, six permutation sets of four frequency bands for each electrode position are framed and the statistical features such as Minimum, Maximum, Mean and Standard Deviation are computed to form the customized feature set. The extracted feature sets are classified using Multilayer Neural Network. Further, the classification models are compared and from the results it is observed that the maximum feature set hits the highest classification accuracy of 88.49%.